[Bug target/93588] Vectorized load followed by FMA pessimizes on Haswell from version 8.1
pinskia at gcc dot gnu.org
gcc-bugzilla@gcc.gnu.org
Wed Feb 5 09:28:00 GMT 2020
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93588
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target| |x86_64-linux-gnu
Status|UNCONFIRMED |WAITING
Last reconfirmed| |2020-02-05
Ever confirmed|0 |1
--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
>The intrinsics are supposed to map to the corresponding assembly instructions, no?
NO, it is an interface to what the assembly instructions do; not always 1-1
mapping. Have you benchmarked both versions?
Also what happens if you use -march=native on your machines? Do the benchmark
for that version is the best?
More information about the Gcc-bugs
mailing list